INDEX

Explanations

elements or structures in programming code

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ÑĢÐµÐ¶Ð´

-0.15

AQ

-0.14

ãģ¨ãģĵãĤį

-0.14

Ð¸Ñī

-0.14

 Future

-0.14

ojis

-0.13

ungan

-0.13

Ð¸ÑĪ

-0.13

vant

-0.13

é¡Ķ

-0.13

POSITIVE LOGITS

anta

0.16

KeyId

0.15

chÃ¡z

0.15

UCT

0.14

alama

0.14

ENSOR

0.14

clc

0.13

 Herman

0.13

Ø§Ø³Ø±

0.13

Activations Density 0.014%

elements or structures in programming code

No Comments

No Known Activations